Update app.py

app.py

@@ -8,7 +8,8 @@ import os
 
 model_name = "microsoft/Phi-3-medium-128k-instruct"
 from transformers import AutoModelForCausalLM, AutoTokenizer
-model = AutoModelForCausalLM.from_pretrained(model_name, device_map='cuda', torch_dtype=torch.float16, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(model_name, device_map='cuda', torch_dtype=torch.float16, trust_remote_code=True
+)
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 
 class StopOnTokens(StoppingCriteria):
@@ -25,7 +26,7 @@ def predict(message, history, temperature, max_tokens, top_p, top_k):
     stop = StopOnTokens()
     messages = "".join(["".join(["\n<|end|>\n<|user|>\n"+item[0], "\n<|end|>\n<|assistant|>\n"+item[1]]) for item in history_transformer_format])
     model_inputs = tokenizer([messages], return_tensors="pt").to("cuda")
-    streamer = TextIteratorStreamer(tokenizer, timeout=300., skip_prompt=True, skip_special_tokens=True)
+    streamer = TextIteratorStreamer(tokenizer, timeout=150., skip_prompt=True, skip_special_tokens=True)
     generate_kwargs = dict(
         model_inputs,
         streamer=streamer,